{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UIXNMWH6N2FLBZMFXOO5NNAKZP","short_pith_number":"pith:UIXNMWH6","schema_version":"1.0","canonical_sha256":"a22ed658fe6e8ab0e585bb9dd6b40acbc340e091b93f30f8255617de2220f03a","source":{"kind":"arxiv","id":"2506.12322","version":2},"attestation_state":"computed","paper":{"title":"Machine Learning Methods for Small Data and Upstream Bioprocessing Applications: A Comprehensive Review","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bogdan Gabrys, Johnny Peng, Katarzyna Musial, Thanh Tung Khuat","submitted_at":"2025-06-14T03:13:05Z","abstract_excerpt":"Data is crucial for machine learning (ML) applications, yet acquiring large datasets can be costly and time-consuming, especially in complex, resource-intensive fields like biopharmaceuticals. A key process in this industry is upstream bioprocessing, where living cells are cultivated and optimised to produce therapeutic proteins and biologics. The intricate nature of these processes, combined with high resource demands, often limits data collection, resulting in smaller datasets. This comprehensive review explores ML methods designed to address the challenges posed by small data and classifies"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.12322","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T03:13:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"95f3e13bcc51d9365e7942563180c9cc9c7faa6ed886f095227455a89730e42a","abstract_canon_sha256":"3ffc933a1ea7a0f265b36af65381b642a39813c3f37903f44b74345133302a71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:23.377533Z","signature_b64":"uN1J3xKyVU45ugv6IIbm/5ewODNE1+uH8DzxqIX3wcxHn0L8fPHVpUtDGOjhDhGvz6++e3G3xHcyUMc1uVAPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a22ed658fe6e8ab0e585bb9dd6b40acbc340e091b93f30f8255617de2220f03a","last_reissued_at":"2026-07-05T11:24:23.376998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:23.376998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Machine Learning Methods for Small Data and Upstream Bioprocessing Applications: A Comprehensive Review","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bogdan Gabrys, Johnny Peng, Katarzyna Musial, Thanh Tung Khuat","submitted_at":"2025-06-14T03:13:05Z","abstract_excerpt":"Data is crucial for machine learning (ML) applications, yet acquiring large datasets can be costly and time-consuming, especially in complex, resource-intensive fields like biopharmaceuticals. A key process in this industry is upstream bioprocessing, where living cells are cultivated and optimised to produce therapeutic proteins and biologics. The intricate nature of these processes, combined with high resource demands, often limits data collection, resulting in smaller datasets. This comprehensive review explores ML methods designed to address the challenges posed by small data and classifies"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12322","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.12322/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.12322","created_at":"2026-07-05T11:24:23.377060+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12322v2","created_at":"2026-07-05T11:24:23.377060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12322","created_at":"2026-07-05T11:24:23.377060+00:00"},{"alias_kind":"pith_short_12","alias_value":"UIXNMWH6N2FL","created_at":"2026-07-05T11:24:23.377060+00:00"},{"alias_kind":"pith_short_16","alias_value":"UIXNMWH6N2FLBZMF","created_at":"2026-07-05T11:24:23.377060+00:00"},{"alias_kind":"pith_short_8","alias_value":"UIXNMWH6","created_at":"2026-07-05T11:24:23.377060+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17539","citing_title":"Reinforcing Dual-Path Reasoning in Spatial Vision Language Models","ref_index":97,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UIXNMWH6N2FLBZMFXOO5NNAKZP","json":"https://pith.science/pith/UIXNMWH6N2FLBZMFXOO5NNAKZP.json","graph_json":"https://pith.science/api/pith-number/UIXNMWH6N2FLBZMFXOO5NNAKZP/graph.json","events_json":"https://pith.science/api/pith-number/UIXNMWH6N2FLBZMFXOO5NNAKZP/events.json","paper":"https://pith.science/paper/UIXNMWH6"},"agent_actions":{"view_html":"https://pith.science/pith/UIXNMWH6N2FLBZMFXOO5NNAKZP","download_json":"https://pith.science/pith/UIXNMWH6N2FLBZMFXOO5NNAKZP.json","view_paper":"https://pith.science/paper/UIXNMWH6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12322&json=true","fetch_graph":"https://pith.science/api/pith-number/UIXNMWH6N2FLBZMFXOO5NNAKZP/graph.json","fetch_events":"https://pith.science/api/pith-number/UIXNMWH6N2FLBZMFXOO5NNAKZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UIXNMWH6N2FLBZMFXOO5NNAKZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UIXNMWH6N2FLBZMFXOO5NNAKZP/action/storage_attestation","attest_author":"https://pith.science/pith/UIXNMWH6N2FLBZMFXOO5NNAKZP/action/author_attestation","sign_citation":"https://pith.science/pith/UIXNMWH6N2FLBZMFXOO5NNAKZP/action/citation_signature","submit_replication":"https://pith.science/pith/UIXNMWH6N2FLBZMFXOO5NNAKZP/action/replication_record"}},"created_at":"2026-07-05T11:24:23.377060+00:00","updated_at":"2026-07-05T11:24:23.377060+00:00"}